Flood risk identification method and device for parking lot, medium and equipment
By constructing and training a flood risk prediction model, and combining historical data and real-time information, safe parking lots are identified and recommended. This solves the problem of accuracy in identifying flood risks in parking lots during severe weather, ensuring the safety of parking lots and drivers.
Patent Information
- Application Number
- CN202410971199.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-19
AI Technical Summary
Existing parking recommendation systems are unable to identify flood risks in a timely and accurate manner during severe weather, which affects parking management and urban transportation systems.
Using a pre-built and trained flood risk prediction model, based on historical hydrological, meteorological, parking lot attributes and protection information, the flood risk index of candidate parking lots is identified, and combined with the number of available parking spaces and distance, target recommended parking lots are determined, generating safe recommendation information.
Accurately identify parking lots at risk of flooding, ensure the safety of recommended parking lots, and reduce losses caused by flooding.
Smart Images

Figure CN118939940A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure belongs to the field of intelligent transportation technology, and in particular relates to a method, device, medium and equipment for identifying flood risks in a parking lot. Background Art
[0002] With the acceleration of urbanization and the impact of climate change, urban floods have become one of the increasingly serious urban disasters. Floods not only have a serious impact on urban transportation systems, but also pose new challenges to parking lot management and urban lifeline engineering construction. In current technical solutions, parking recommendation systems mostly recommend parking lots to drivers based on the availability of parking spaces and the distance between the vehicle and the parking lot. However, when there is severe weather (such as heavy rain, etc.), it is impossible to promptly and accurately determine parking lots with flood risks, resulting in corresponding losses. Summary of the invention
[0003] The embodiments of the present application provide a method, device, medium and equipment for identifying flood risks in parking lots, which can accurately identify parking lots with flood risks to at least a certain extent, thereby ensuring the safety of the recommended parking lots.
[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.
[0005] According to one aspect of the present application, a method for identifying flood risks in parking lots is provided, comprising: determining, based on a current position of a target vehicle, a candidate parking lot that is within a first predetermined range of the current position and has available parking spaces; using a pre-constructed and trained flood risk prediction model to predict flood risks for each of the candidate parking lots, and obtaining a flood risk index corresponding to each of the candidate parking lots, the flood risk prediction model being trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information; determining at least one target recommended parking lot from the candidate parking lots based on the flood risk index corresponding to each of the candidate parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle; and generating and pushing corresponding recommendation information based on the at least one target recommended parking lot.
[0006] According to an embodiment of the present application, at least one target recommended parking lot is determined from the to-be-selected parking lots based on the flood risk index corresponding to each of the to-be-selected parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle, including: determining a recommendation score corresponding to each of the to-be-selected parking lots based on the flood risk index corresponding to each of the to-be-selected parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle; and determining a to-be-selected parking lot whose recommendation score meets a predetermined rule as a target recommended parking lot.
[0007] According to one embodiment of the present application, corresponding recommendation information is generated and pushed based on the at least one target recommended parking lot, including: obtaining the currently confirmed affected parking lots and affected road sections; for other parking lots in the target recommended parking lots except the affected parking lot, corresponding recommendation information is generated and pushed, and the recommendation information includes a navigation route that avoids the affected road section.
[0008] According to one embodiment of the present application, the method also includes: based on the flood risk prediction model, predicting the flood risk of the monitored parking lots within the second predetermined range to obtain a corresponding flood risk index; and selecting and executing a corresponding vehicle evacuation strategy based on the flood risk index corresponding to each of the monitored parking lots and the number of parked vehicles.
[0009] According to an embodiment of the present application, according to the flood risk index and the number of parked vehicles corresponding to each monitored parking lot, a corresponding vehicle evacuation strategy is selected and executed, including: when the flood risk index of the monitored parking lot is in a first numerical interval, no vehicle evacuation is performed; when the flood risk index of the monitored parking lot is in a second numerical interval, the current maximum number of parked vehicles in the monitored parking lot is determined according to the available parking space ratio threshold corresponding to the second numerical interval; when the maximum number of parked vehicles is less than the number of parked vehicles in the monitored parking lot, the vehicles to be transferred in the monitored parking lot are determined and a transfer vehicle prompt message is sent to the corresponding owner; when the flood risk index of the monitored parking lot is greater than the value in the second numerical interval, a transfer vehicle prompt message is sent to the owner of the parked vehicle in the monitored parking lot.
[0010] According to one embodiment of the present application, determining the vehicles to be transferred in the monitored parking lot includes: determining a minimum threshold value for the number of vehicles to be transferred based on the current maximum number of parking spaces and the number of vehicles already parked in the monitored parking lot; determining the vehicles to be transferred from the parked vehicles in the monitored parking lot based on the minimum threshold value for the number of vehicles to be transferred and the entry time, vehicle type and parking position of the parked vehicles in the monitored parking lot.
[0011] According to an embodiment of the present application, the flood risk prediction model includes several decision trees, and a corresponding flood risk index is generated by integrating the flood risk prediction results of several decision trees.
[0012] According to another aspect of the present application, a flood risk identification device for a parking lot is provided, comprising: a determination module, for determining, based on a current position of a target vehicle, a candidate parking lot that is within a first predetermined range of the current position and has available parking spaces; a prediction module, for using a pre-constructed and trained flood risk prediction model to perform flood risk prediction on each of the candidate parking lots, and obtain a flood risk index corresponding to each of the candidate parking lots, wherein the flood risk prediction model is trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information; a selection module, for determining at least one target recommended parking lot from the candidate parking lots, based on the flood risk index corresponding to each of the candidate parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle; and a processing module, for generating and pushing corresponding recommendation information based on the at least one target recommended parking lot.
[0013] According to another aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for identifying flood risks in a parking lot as described in any one of the above items is implemented.
[0014] According to another aspect of the present application, an electronic device is provided, characterized in that it includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the flood risk identification method for the parking lot as described in any one of the above.
[0015] In the technical solutions provided in some embodiments of the present application, according to the current position of the target vehicle, a candidate parking lot located within the first predetermined range of the current position and having available parking spaces is determined, and a pre-built and trained flood risk prediction model is used to predict flood risks for each candidate parking lot, and a flood risk index corresponding to each candidate parking lot is obtained. The flood risk prediction model is trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information. Then, according to the flood risk index corresponding to each candidate parking lot, the number of available parking spaces, and the distance from the current position of the target vehicle, at least one target recommended parking lot is determined from the candidate parking lots, and then corresponding recommendation information is generated and pushed based on the at least one target recommended parking lot. Therefore, before recommending a parking lot, a pre-trained flood risk prediction model is used to predict flood risks for each candidate parking lot to obtain a corresponding flood risk index, and then the target recommended parking lot is determined based on the flood risk index and other information, so that the flood risk of each candidate parking lot can be accurately identified, thereby ensuring the safety of the recommended parking lot.
[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0018] Figure 1 A schematic flow chart of a method for identifying flood risk in a parking lot according to an embodiment of the present application is shown.
[0019] Figure 2 A block diagram of a flood risk identification device for a parking lot according to an embodiment of the present application is shown.
[0020] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION
[0021] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.
[0022] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.
[0023] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0024] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0025] Figure 1 A schematic flow chart of a method for identifying flood risk in a parking lot according to an embodiment of the present application is shown.
[0026] The method can be applied to a terminal device or a server, wherein the terminal device may include but is not limited to one or more of a smart phone, a tablet computer, a portable computer, and a desktop computer; the server may be a physical server or a cloud server.
[0027] Please refer to Figure 1 The parking lot flood risk identification method at least includes steps S110 to S140, which are described in detail as follows: (The following is an example of the method being applied to a server) In step S110, according to the current position of the target vehicle, a parking lot to be selected that is within a predetermined range of the current position and has vacant parking spaces is determined.
[0028] The target vehicle may be a vehicle currently requesting a recommended parking lot.
[0029] In one embodiment, the driver of the target vehicle can communicate with the server through the vehicle terminal and send a request for a parking lot recommendation to the server. After receiving the request, the server can obtain the current location of the target vehicle, which can be obtained by the positioning system of the target vehicle itself.
[0030] Next, the server can determine a parking lot within a first predetermined range of the current position according to the acquired current position of the target vehicle, wherein the first predetermined range can be pre-set by a person skilled in the art according to prior experience, for example, a developer can determine the maximum parking distance acceptable to most drivers according to statistical results as the first predetermined range. In other examples, the first predetermined range can also be specified by the driver of the target vehicle, for example, when the current weather is bad, the driver can select a shorter distance as the first predetermined range.
[0031] It should be noted that those skilled in the art may select a corresponding method for determining the first predetermined range according to actual implementation requirements, and no special limitation is imposed on this.
[0032] After determining the parking lot within the first predetermined range, the server can obtain relevant information of each parking lot within the range to determine whether the parking lot has available parking spaces. In one example, the server can access the backend of each parking lot to obtain relevant information such as the number of parking spaces and the number of cars parked in the parking lot, and then determine whether the parking lot has available parking spaces.
[0033] When it is determined that a parking lot is located within the first predetermined range of the current position of the target vehicle and has available parking spaces, the parking lot can be determined as a parking lot to be selected. It should be understood that the number of the parking lots to be selected can be one, two, or more than two, and there is no special limitation on this.
[0034] In step S120, a pre-constructed and trained flood risk prediction model is used to predict flood risks for each of the selected parking lots to obtain a flood risk index corresponding to each of the selected parking lots. The flood risk prediction model is trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information.
[0035] In this embodiment, those skilled in the art may pre-construct and train a flood risk prediction model, which may be used to predict the flood risk of each parking lot based on relevant information and output a corresponding flood risk index.
[0036] After the parking lots to be selected are determined, the server can call the trained flood risk prediction model to predict the flood risk of each parking lot to obtain the flood risk index corresponding to each parking lot to be selected. It should be understood that the flood risk index is used to characterize the possibility of the parking lot to be selected suffering from flood disasters in the future. If the flood risk index of a parking lot is larger, it means that the possibility of the parking lot to be selected suffering from flood disasters is greater. Conversely, if the flood risk index is smaller, the possibility of the parking lot to be suffered from flood disasters is smaller.
[0037] In one embodiment, when training a flood risk prediction model, technicians in this field may pre-acquire corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information to train the flood risk prediction model.
[0038] Specifically, the historical hydrological data may include but is not limited to information such as the water level height and duration of historical floods; the historical meteorological data may include but is not limited to meteorological data such as rainfall and rainfall intensity; the parking lot attribute information may include but is not limited to the geographic information of the parking lot (such as altitude, slope, etc.), the structural information of the parking lot itself (such as underground parking lot, open-air parking lot, structural airtightness of parking lot building, etc.) and the surrounding environment information of the parking lot (such as the straight-line distance to the nearest river or lake, the distribution density of surrounding water systems, and historical flood data in the surrounding area); the parking lot flood data may include but is not limited to information such as whether the parking lot has been flooded in history, the water level depth when flooded, and the duration of flooding; the parking lot flood protection information may include the existence or non-existence of the parking lot's flood control facilities (such as flood cofferdams, water retaining facilities, etc.), drainage systems (such as the number of drainage pipes, drainage efficiency, etc.), etc., as well as the historical record of the parking lot manager's response to flood warning information.
[0039] Therefore, training the flood risk prediction model based on the above historical data can enable the flood risk prediction model to comprehensively consider various factors when making flood risk predictions, thereby ensuring the accuracy of the output flood risk index.
[0040] In one example, after acquiring the above historical data, data preprocessing may be performed first, and the data preprocessing may include data cleaning and data filling, so as to improve the quality of training data and ensure the subsequent training effect.
[0041] In one embodiment, the flood risk prediction model may include several decision trees, and the corresponding flood risk index is generated by combining the flood risk prediction results of several decision trees. Specifically, assuming that the number of decision trees in the flood risk prediction model is N, during the training process, for a given sample data X, which contains the water level height of historical floods, flooded parking lots and their water level depth, flooding duration, rainfall, rainfall intensity and other characteristics, the flood risk assessment prediction calculation formula of the flood risk prediction model is as follows: .
[0042] in, RiskScore is the flood risk index, N is the number of decision trees, For the i A decision tree for sample data X The prediction function of is the model parameter.
[0043] Introducing specific factors into random forests and gradient boosting trees, including parking lot geographic information factors F 1 , Parking lot surrounding environmental factors F 2 , Parking lot structure factors F 3 , Human intervention factors F 4 Among them, the geographic information factor is obtained from the geographic information of the parking lot contained in the parking lot attribute information, the surrounding environment factor of the parking lot is obtained from the surrounding environment information of the parking lot; the parking lot structure factor is obtained from the structural information of the parking lot itself; and the artificial intervention factor is obtained from the flood protection information of the parking lot.
[0044] The server can encode the corresponding information according to the predetermined rules to obtain the vector representation of each factor. For example, a binary variable can be used to represent the presence or absence of flood control facilities, such as 1 for the presence of flood control facilities and 0 for the absence of flood control facilities; the efficiency of the drainage system can be represented by the efficiency score of the drainage system, and the score range can be 0-1 to represent the relative efficiency of the drainage system under flood conditions.
[0045] The response of parking lot managers to flood warning information can be represented by the response speed and response measures. For the response speed, it can be quantified based on how long it takes managers to take action after the flood warning is issued. For example, the score for responding within 1 hour after the warning is issued is 1, and the score for not responding for more than 4 hours is 0. The scores at other time points are calculated according to linear or nonlinear functions. For the response measures, the scores are given according to the effectiveness of the measures taken. For example, the score for installing and effectively installing temporary flood control facilities is 1, and the score for not taking any response measures is 0, etc.
[0046] According to the specific factors introduced, the decision tree construction and training formula is as follows: , Right now .
[0047] This formula describes how a single decision tree predicts in a random forest, where For the i The prediction function of a decision tree. M is the number of leaf nodes in the decision tree. It is j The weight coefficient of a leaf node, It is j The predicted value of a leaf node, θ i,j For the i In the decision tree j Model parameters related to features need to be explained. θ i,j The value of can be determined through the training process, which is used to represent the split point, feature selection, leaf node output value and weight coefficient after introducing specific factors in the decision tree, so as to optimize the prediction ability of the model; F is a specific factor vector, is the weight coefficient of a specific factor, , , as well as Parking lot geographic information factors F 1 , Parking lot surrounding environmental factors F 2 , Parking lot structure factors F 3 , Human intervention factors F 4 Corresponding weight coefficients. In one example, the weight coefficients of specific factors can be optimized through methods such as cross-validation and grid search to ensure the accuracy of the prediction results of the decision tree.
[0048] Therefore, the flood risk prediction model provided by the embodiment of the present application introduces specific factors for flood risk prediction on the basis of the traditional decision tree, thereby enhancing the prediction ability of the decision tree. The flood risk prediction model thus obtained can more comprehensively and accurately predict the flood risk of parking lots under severe weather.
[0049] Please continue to refer to Figure 1In step S130, at least one target recommended parking lot is determined from the candidate parking lots according to the flood risk index, the number of available parking spaces, and the distance from the current position of the target vehicle corresponding to each of the candidate parking lots.
[0050] In one embodiment, step S130 includes: determining a recommendation score corresponding to each of the candidate parking lots according to the flood risk index corresponding to each of the candidate parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle; and determining a candidate parking lot whose recommendation score meets a predetermined rule as a target recommended parking lot.
[0051] In this embodiment, after determining the flood risk index of each candidate parking lot, the server can score each candidate parking lot according to the flood risk index of each candidate parking lot, the number of available parking spaces, and the distance between the candidate parking lot and the current position of the target vehicle to obtain a corresponding recommendation score.
[0052] In one example, assuming that there are n parking lots to be selected, numbered 1, 2, ..., n, the weighted sum of the distance weighted score, the weighted score of the number of available parking spaces, and the weighted score of flood risk is weighted to obtain the recommendation score corresponding to the parking lot to be selected. The calculation formula is as follows: ,in, w d , w a and w f They are the weights of the distance-weighted score, the available parking spaces-weighted score, and the flood risk-weighted score, respectively.
[0053] For distance-weighted scoring, the server can calculate the distance between itself and the target vehicle's current location and convert it into a distance-weighted score. D i , , d i Indicates the current location of the target vehicle and the parking lot i The closer the distance, the higher the distance weighted score.
[0054] For the weighted score of the number of available parking spaces, the server can calculate the ratio of the number of available parking spaces to the total number of parking spaces and convert it into a weighted score of the number of available parking spaces. A i , A i = a i / A , a i For parking lot iThe number of available parking spaces, A Indicates parking lot i The more available parking spaces there are, the higher the weighted score of the available parking spaces is.
[0055] For the flood risk weighted score, the corresponding flood risk level can be determined according to the value of the flood risk index, and then different weights are given according to different flood risk levels to convert it into a flood risk weighted score. F i , ,in, Risk i Indicates parking lot i The flood risk level Weight ( Risk i ) is the weight corresponding to the flood risk level. The lower the flood risk level, the higher the flood risk weighted score.
[0056] Thus, the server can determine the recommendation score corresponding to each parking lot to be selected based on the above-mentioned calculation rule of the recommendation score. In one example, the server can select a predetermined number of parking lots to be selected with the largest recommendation scores as target recommended parking lots. In another example, the server can also determine the parking lot to be selected with the highest recommendation score as the best parking lot, and determine the parking lot to be selected with the second highest recommendation score as the alternative parking lot, so as to recommend the best parking lot and the alternative parking lot as the target recommended parking lot.
[0057] Please continue to refer to Figure 1 In step S140, corresponding recommendation information is generated and pushed according to the at least one target recommended parking lot.
[0058] In this embodiment, the server can calculate the distance between the target vehicle and each target recommended parking lot based on the determined target recommended parking lot and the current position of the target vehicle, and generate a corresponding navigation route, based on which corresponding recommendation information is generated and pushed. In one example, the server can push the recommendation information to the vehicle-mounted terminal of the target vehicle for display, so that the driver of the target vehicle can select it. In another example, the server can also push the recommendation information to the mobile terminal carried by the driver of the target vehicle for display.
[0059] It is worth noting that when the server communicates with the mobile terminal carried by the driver of the target vehicle, the aforementioned "current position of the target vehicle" can be obtained by the positioning device of the mobile terminal itself, that is, the current position of the mobile terminal is used as the current position of the target vehicle for subsequent processing.
[0060] In one embodiment, corresponding recommendation information is generated and pushed based on the at least one target recommended parking lot, including: obtaining the currently confirmed affected parking lots and affected road sections; for other parking lots in the target recommended parking lots except the affected parking lots, corresponding recommendation information is generated and pushed, and the recommendation information includes a navigation route that avoids the affected road section.
[0061] In one embodiment, the server can obtain real-time data from the city traffic management department, which usually includes information about the road sections that have been affected by the disaster. The server can also obtain real-time data from the city management system to determine which parking lots or roads have been marked as flood disaster affected areas.
[0062] In another embodiment, the server may also extract and analyze flood-related information by real-time monitoring of social media and news websites. In addition, social media users often post photos and descriptions of disaster situations, which may also serve as a supplement to real-time data.
[0063] In yet another embodiment, the server may also utilize an open flood disaster data interface on the Internet (eg, an API provided by a meteorological bureau, a disaster warning center, etc.) to obtain the latest flood disaster information.
[0064] The server can integrate and filter the real-time data obtained in the above ways, that is, it can integrate and filter sensor data, traffic management department data, urban management system data, and Internet real-time data to determine which parking lots and road sections are currently affected by floods, and then determine the affected parking lots and road sections.
[0065] Next, after determining the affected parking lots and the affected road sections, the server can filter and remove the affected parking lots in the target recommended parking lots, and then generate and push corresponding recommendation information based on the remaining target recommended parking lots. The recommendation information can include navigation routes to the remaining target recommended parking lots, and the navigation routes have avoided the affected road sections, thereby ensuring that the target vehicles are not affected by the flood disaster on the way to the parking lot, ensuring their safety.
[0066] Therefore, based on Figure 1In the embodiment shown, according to the current position of the target vehicle, a candidate parking lot located within the first predetermined range of the current position and having available parking spaces is determined, and a pre-built and trained flood risk prediction model is used to predict flood risks for each candidate parking lot, and a flood risk index corresponding to each candidate parking lot is obtained. The flood risk prediction model is trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information. Then, according to the flood risk index corresponding to each candidate parking lot, the number of available parking spaces, and the distance from the current position of the target vehicle, at least one target recommended parking lot is determined from the candidate parking lots, and then corresponding recommendation information is generated and pushed based on the at least one target recommended parking lot. Therefore, before recommending a parking lot, a pre-trained flood risk prediction model is used to predict flood risks for each candidate parking lot to obtain a corresponding flood risk index, and then the target recommended parking lot is determined based on the flood risk index and other information, so that the flood risk of each candidate parking lot can be accurately identified, thereby ensuring the safety of the recommended parking lot.
[0067] In one embodiment of the present application, the method for identifying flood risks in the parking lot also includes: based on the flood risk prediction model, identifying flood risks for the monitored parking lots within the second predetermined range to obtain corresponding flood risk indexes; and selecting and executing corresponding vehicle evacuation strategies based on the flood risk index corresponding to each of the monitored parking lots and the number of vehicles parked.
[0068] In this embodiment, in addition to responding to the user's request to perform flood risk prediction, the server can also actively perform flood risk prediction for the monitored parking lots within the second predetermined range according to a predetermined period to obtain a flood risk index corresponding to each monitored parking lot.
[0069] The second predetermined range may be a certain district / county, a certain city, etc. Technical personnel in this field may determine the coverage of the second predetermined range according to actual implementation needs, and no special limitation is made to this.
[0070] The monitored parking lot may be a parking lot that is subject to flood risk monitoring at the request of its management personnel. In other examples, the server may also proactively include parking lots that are within the second predetermined range and meet the corresponding flood risk prediction requirements (for example, meet relevant data acquisition requirements or permissions, etc.) as monitored parking lots.
[0071] After determining the flood risk index corresponding to each monitored parking lot, the server can select and execute the corresponding vehicle evacuation strategy according to the corresponding flood risk index and the number of vehicles parked in the monitored parking lot. The vehicle evacuation strategy can be a protective measure pre-set by a person skilled in the art to ensure the safety of vehicles in the parking lot.
[0072] In one embodiment, according to the flood risk index and the number of parked vehicles corresponding to each monitored parking lot, a corresponding vehicle evacuation strategy is selected and executed, including: when the flood risk index of the monitored parking lot is in a first numerical interval, no vehicle evacuation is performed; when the flood risk index of the monitored parking lot is in a second numerical interval, the current maximum number of available parking spaces in the monitored parking lot is determined according to the available parking space ratio threshold corresponding to the second numerical interval; when the maximum number of parked vehicles is less than the number of parked vehicles in the monitored parking lot, the vehicles to be transferred in the monitored parking lot are determined and a transfer vehicle prompt message is sent to the corresponding owner; when the flood risk index of the monitored parking lot is greater than the value in the second numerical interval, a transfer vehicle prompt message is sent to the owner of the parked vehicle in the monitored parking lot.
[0073] In this embodiment, when the flood risk index corresponding to the monitored parking lot is in the first numerical range, it indicates that the monitored parking lot is less likely to suffer from flood disasters. At this time, no matter how many vehicles are parked in the monitored parking lot, vehicle evacuation may not be performed.
[0074] When the flood risk index of the monitored parking lot is in the second numerical interval, where the value in the second numerical interval is greater than the value in the first interval, it means that the monitored parking lot has a certain risk of being affected by floods. Therefore, the server can take measures to restrict parking in the monitored parking lot, temporarily close the parking lot or limit the number of parking spaces, and update the parking lot status on the system to reduce the risk of floods, prevent new vehicles from entering the affected area, and reduce losses.
[0075] When limiting the number of parking spaces, the server can determine the maximum number of parking spaces available in the monitored parking lot according to the available parking space ratio threshold value corresponding to the second numerical interval. For example, assuming that the total number of parking spaces in the monitored parking lot is 200 and the available parking space ratio threshold value corresponding to the current state is 0.5, the maximum number of parking spaces available in the monitored parking lot is 200×0.5=100. If the available parking space ratio threshold value is 0.3, the corresponding maximum number of parking spaces available is 200×0.3=60, etc. It should be understood that the maximum number of parking spaces available refers to the number of vehicles that have already parked in the monitored parking lot, rather than the number of vehicles that can still park in the monitored parking lot.
[0076] In one example, after determining the maximum number of available parking spaces, the server can update the maximum number of available parking spaces in the parking lot management system. Based on the number of vehicles parked in the monitored parking lot, the system can update the number of remaining available parking spaces and notify the parking lot manager and user. The parking lot manager can control vehicles entering the monitored parking lot according to the system prompt. The server can also monitor the use of parking spaces in the monitored parking lot in real time through sensors and / or cameras to dynamically adjust the number of remaining available parking spaces according to actual conditions.
[0077] The server can compare the maximum number of available parking spaces with the number of vehicles already parked in the monitored parking lot. If the number of vehicles already parked is less than or equal to the maximum number of available parking spaces, no processing can be performed or vehicles can be restricted from continuing to enter the parking lot. If the number of vehicles already parked is greater than the maximum number of available parking spaces, the vehicles in the monitored parking lot need to be evacuated, and the server can send a vehicle transfer prompt message to the car owner, thereby suggesting that some vehicles be transferred to other safe parking lots (the method for determining safe parking lots can be determined by the method provided in the aforementioned embodiment, which will not be repeated here).
[0078] In one example, the server may send a vehicle transfer prompt message to all owners of vehicles in the monitored parking lot, so that each owner can choose whether to transfer the vehicle until the number of parked vehicles is less than or equal to the maximum number of available parking spaces.
[0079] In another example, the server may subtract the number of vehicles parked in the monitored parking lot from the maximum number of available parking spaces, thereby obtaining the corresponding minimum threshold number of vehicles that need to be transferred. It should be understood that the minimum threshold number of vehicles that need to be transferred represents the minimum number of vehicles that should be transferred in the monitored parking lot.
[0080] Next, the server can determine the vehicles to be transferred from the parked vehicles in the monitored parking lot according to the minimum threshold of the number of vehicles to be transferred, as well as the entry time, vehicle type and parking position of the parked vehicles in the monitored parking lot. It should be understood that the number of vehicles to be transferred can be equal to the minimum threshold of the number of vehicles to be transferred, and it can also be greater than the number of vehicles to be transferred, so as to avoid some car owners being unwilling or unable to transfer their vehicles in time.
[0081] Specifically, based on the entry time, the server can determine the parking time of each vehicle, so that when determining the vehicles to be transferred, the server will give priority to recommending that vehicles with shorter parking times be transferred to other parking lots, thereby ensuring that car owners can find parking spaces more easily and reducing interference with long-term parked vehicles. In addition, vehicles with shorter parking times are relatively flexible, and car owners are more willing to cooperate with temporary adjustments.
[0082] Regarding vehicle types, priority can be given to small cars that are easy to move or vehicles without special requirements (such as electric vehicles requiring charging stations), so that large vehicles and vehicles with special needs should not be adjusted as much as possible to avoid inconvenience.
[0083] As for the parking location, the server can give priority to recommending the relocation of vehicles located in areas that are prone to floods (such as low-lying areas or areas with poor drainage) based on the geographical location of the parking lot and the parking location of the vehicle.
[0084] For the above three factors, the server can give priority to a comprehensive consideration approach, which will help improve the rationality of determining the vehicles to be transferred.
[0085] In addition, the server may also provide rewards (such as parking fee coupons, etc.) to the car owner when sending the vehicle transfer reminder information to encourage the car owner to cooperate in moving the car. The server may send the vehicle transfer reminder information to the car owner via SMS, WeChat public account, etc.
[0086] When the flood risk index corresponding to the monitored parking lot is greater than the value in the second numerical range, it indicates that the monitored parking lot is more likely to be affected by flood disasters. At this time, the server can send a vehicle transfer reminder message to the owners of the vehicles parked in the monitored parking lot to remind them to transfer the vehicles in the monitored parking lot as soon as possible to avoid or reduce property losses. Similarly, the server can include a safe parking lot and a corresponding route recommendation in the vehicle transfer reminder message to facilitate the owner to determine the transfer destination as soon as possible.
[0087] In one embodiment of the present application, after the flood risk prediction model is launched, the server can monitor and adjust it in real time to respond to changing environmental factors and data changes in a timely manner to ensure the accuracy of the model's prediction results.
[0088] The server can also collect data after actual flood events occur, and / or collect feedback information from drivers (including the actual situation of the parking lot, the accuracy of the parking lot recommendation, etc.) to provide feedback and improve the flood risk prediction model and improve the prediction performance of the model.
[0089] Based on the above factors, the server can give priority to a comprehensive consideration method, through a unified feedback and adjustment of all factors. This helps to comprehensively improve the performance and reliability of the system. Of course, if the factors are considered separately, it will help to optimize the specific problems in depth. In practical applications, those skilled in the art can choose a suitable method according to the specific situation, or combine the advantages of the two methods to perform comprehensive optimization, and this application does not make any special restrictions on this.
[0090] In one embodiment, the server may optimize the flood risk prediction model in the following manner.
[0091] (1) Real-time monitoring and dynamic adjustment: The flood risk prediction model is dynamically adjusted based on real-time data to ensure that the model can reflect current environmental changes in a timely manner.
[0092] (2) Feedback of actual events for model correction: Feed the data of actual events into the model for error analysis and correction to improve the model’s prediction accuracy.
[0093] (3) Algorithm optimization based on driver feedback: Improve the recommendation algorithm based on driver feedback, such as adjusting the scoring weight and optimizing the recommendation logic.
[0094] Specifically, in the above (1), it may include the following steps.
[0095] 1. Data Preprocessing a. Data cleaning b. Data Fusion Time synchronization: synchronize the data from different data sources to ensure that the timestamps of each data source are consistent; Spatial fusion: spatially fuse data from different locations to establish a unified urban flood monitoring dataset.
[0096] 2. Real-time model calculation a. Data Input Input the real-time collected and pre-processed data into the flood risk prediction model, including hydrological data, meteorological data, traffic data and parking lot status data; b. Model update Dynamically adjust model parameters: Dynamically adjust the parameters of the flood risk prediction model based on real-time data to ensure that the model can accurately reflect current environmental changes; Real-time prediction and calculation: Use real-time data to predict flood risks and calculate the flood risk index for each parking lot.
[0097] 3. Real-time monitoring and alarm a. Risk monitoring Real-time monitoring system: Establish a real-time monitoring system to monitor the changes in the flood risk index of each parking lot; Threshold setting: Set the alarm threshold of the flood risk index. When the flood risk index of a parking lot exceeds the alarm threshold, the alarm mechanism is triggered; b. Early warning notification.
[0098] 4. Real-time adjustment and optimization a. Data Feedback Feedback on actual flood events: Collect data on actual flood events, including information on parking lot impact, time, and water level; User feedback: Collect user feedback on flood warning information, including the accuracy of warnings and responses; b. Model Adjustment Error analysis: Analyze the error between the model prediction and the actual situation, and determine the factors that affect the accuracy of the prediction; Parameter optimization: According to the error analysis results, the model parameters are optimized and adjusted to improve the prediction accuracy of the model; Model training: Retrain the model using new data sets to ensure that the model can adapt to the latest environmental changes and data characteristics.
[0099] Therefore, by continuously tuning the flood risk prediction model in the above manner, the accuracy of the prediction results of the flood risk prediction model can be ensured.
[0100] In the above (2), the actual event data used may include the following.
[0101] 1. Hydrological data Water level: water level changes during floods, including peak water levels and duration; Flow rate: the speed of water flow during floods; Water depth: the depth of water in each affected area; Flood spread: The geographical scope and spread speed of the impact of flood events.
[0102] 2. Weather data Rainfall: total rainfall and rainfall distribution during the flood period; Rainfall intensity: the intensity and duration of rainfall; Temporal distribution of rainfall: the specific time period and frequency of rainfall occurrence.
[0103] 3. Parking lot data Parking lot information affected: which parking lots were affected and the extent of the impact (e.g., completely flooded, partially flooded); Parking lot location: The geographic location of the affected parking lot; Parking space status: parking space usage of the affected parking lot during the flood period, including the number of vehicles in the parking lot and the damage; Parking lot structure: Structural characteristics of the affected parking lot (e.g. underground parking lot, open-air parking lot, etc.).
[0104] 4. Traffic data Damage to road sections: which roads were affected by flooding, the extent and scope of the damage; Traffic flow changes: changes in traffic flow during and after floods; Traffic conditions: which roads are completely blocked and which roads are partially restricted.
[0105] 5. Flood control facility data Status of flood control facilities: the operation of flood control facilities during floods, such as the working status of drainage systems, the effectiveness of flood walls, etc.; Facility failure situation: whether there is any failure in flood control facilities, the specific situation and impact of the failure.
[0106] 6. Socioeconomic data Economic losses: direct and indirect economic losses caused by floods, including vehicle losses, parking facility losses, etc.; Impact on personnel: The impact of flooding on car owners and parking lot managers, such as personnel evacuation, property loss, etc.
[0107] 7. User feedback data Warning feedback: feedback from car owners and parking lot managers on flood warning information, including the timeliness and accuracy of the warning; Dispatch Feedback: Feedback on vehicle dispatch recommendations, including dispatch effectiveness and execution.
[0108] 8. Environmental Data Topographic changes: changes in topography after floods, such as ground subsidence, geological disasters, etc.
[0109] Therefore, by obtaining one or more of the above actual event data to optimize the flood risk prediction model, the accuracy of the prediction results of the flood risk prediction model can be improved.
[0110] The following describes an apparatus embodiment of the present application, which can be used to execute the parking lot flood risk identification method in the above-mentioned embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the above-mentioned parking lot flood risk identification method embodiment of the present application.
[0111] Figure 2 A block diagram of a flood risk identification device for a parking lot according to an embodiment of the present application is shown.
[0112] Reference Figure 2As shown, a flood risk identification device for a parking lot according to an embodiment of the present application includes: a determination module, used to determine, based on the current position of a target vehicle, a candidate parking lot that is located within a first predetermined range of the current position and has available parking spaces; a prediction module, used to use a pre-constructed and trained flood risk prediction model to perform flood risk prediction on each of the candidate parking lots, and obtain a flood risk index corresponding to each of the candidate parking lots, wherein the flood risk prediction model is trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information; a selection module, used to determine at least one target recommended parking lot from the candidate parking lots based on the flood risk index corresponding to each of the candidate parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle; a processing module, used to generate and push corresponding recommendation information based on the at least one target recommended parking lot.
[0113] In one embodiment of the present application, at least one target recommended parking lot is determined from the candidate parking lots based on the flood risk index corresponding to each of the candidate parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle, including: determining the recommendation score corresponding to each of the candidate parking lots based on the flood risk index corresponding to each of the candidate parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle; and determining the candidate parking lot whose recommendation score meets a predetermined rule as the target recommended parking lot.
[0114] In one embodiment of the present application, corresponding recommendation information is generated and pushed based on the at least one target recommended parking lot, including: obtaining the currently confirmed affected parking lots and affected road sections; for other parking lots in the target recommended parking lots except the affected parking lot, corresponding recommendation information is generated and pushed, and the recommendation information includes a navigation route that avoids the affected road section.
[0115] In one embodiment of the present application, the prediction module is also used to: based on the flood risk prediction model, predict flood risks for the monitored parking lots within the second predetermined range to obtain corresponding flood risk indexes; and select and execute corresponding vehicle evacuation strategies according to the flood risk index corresponding to each of the monitored parking lots and the number of parked vehicles.
[0116] In one embodiment of the present application, according to the flood risk index and the number of parked vehicles corresponding to each monitored parking lot, a corresponding vehicle evacuation strategy is selected and executed, including: when the flood risk index of the monitored parking lot is in a first numerical interval, no vehicle evacuation is performed; when the flood risk index of the monitored parking lot is in a second numerical interval, the current maximum number of parked vehicles in the monitored parking lot is determined according to the available parking space ratio threshold corresponding to the second numerical interval; when the maximum number of parked vehicles is less than the number of parked vehicles in the monitored parking lot, the vehicles to be transferred in the monitored parking lot are determined and a transfer vehicle prompt message is sent to the corresponding owner; when the flood risk index of the monitored parking lot is greater than the value in the second numerical interval, a transfer vehicle prompt message is sent to the owner of the parked vehicle in the monitored parking lot.
[0117] In one embodiment of the present application, determining the vehicles to be transferred in the monitored parking lot includes: determining a minimum threshold value for the number of vehicles to be transferred based on the current maximum number of parking spaces and the number of vehicles already parked in the monitored parking lot; determining the vehicles to be transferred from the parked vehicles in the monitored parking lot based on the minimum threshold value for the number of vehicles to be transferred and the entry time, vehicle type and parking location of the parked vehicles in the monitored parking lot.
[0118] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.
[0119] It should be noted that Figure 3 The computer system of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0120] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.
[0121] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.
[0122] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the system of the present application are executed.
[0123] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable storage media include, for example, but are not limited to: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0124] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0125] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0126] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.
[0127] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0128] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.
[0129] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.
[0130] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A method for identifying flood risk in parking lots, It is characterized in that include: Determine, according to the current position of the target vehicle, a parking lot to be selected that is within a first predetermined range of the current position and has available parking spaces; A flood risk prediction model constructed and trained in advance is used to predict flood risks for each of the selected parking lots, and a flood risk index corresponding to each of the selected parking lots is obtained. The flood risk prediction model is trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information. The flood risk prediction model includes several decision trees, and the corresponding flood risk index is generated by integrating the flood risk prediction results of several decision trees. Determine at least one target recommended parking lot from the candidate parking lots according to the flood risk index, the number of available parking spaces, and the distance from the current position of the target vehicle corresponding to each of the candidate parking lots; According to the at least one target recommended parking lot, corresponding recommendation information is generated and pushed.
2. The method according to claim 1, It is characterized in that Determining at least one target recommended parking lot from the candidate parking lots according to the flood risk index, the number of available parking spaces, and the distance from the current position of the target vehicle corresponding to each of the candidate parking lots includes: Determine a recommendation score corresponding to each of the to-be-selected parking lots according to the flood risk index corresponding to each of the to-be-selected parking lots, the number of available parking spaces, and the distance from the current position of the target vehicle; The candidate parking lot whose recommendation score meets the predetermined rules is determined as the target recommended parking lot.
3. The method according to claim 2, It is characterized in that Recommending a parking lot according to the at least one target, generating and pushing corresponding recommendation information, including: Obtain the currently confirmed affected parking lots and affected road sections; For parking lots other than the disaster-affected parking lot in the target recommended parking lot, corresponding recommendation information is generated and pushed, wherein the recommendation information includes a navigation route that has avoided the disaster-affected road section.
4. The method according to claim 1, It is characterized in that The method further comprises: Based on the flood risk prediction model, a flood risk prediction is performed on the monitored parking lot within the second predetermined range to obtain a corresponding flood risk index; According to the flood risk index corresponding to each monitored parking lot and the number of vehicles parked, a corresponding vehicle evacuation strategy is selected and executed.
5. The method according to claim 4, It is characterized in that According to the flood risk index corresponding to each monitored parking lot and the number of vehicles parked, a corresponding vehicle evacuation strategy is selected and executed, including: When the flood risk index of the monitored parking lot is within the first value range, no vehicle evacuation is performed; When the flood risk index of the monitored parking lot is within the second numerical range, the maximum number of available parking spaces in the monitored parking lot is determined according to the available parking space ratio threshold corresponding to the second numerical range; when the maximum number of available parking spaces is less than the number of vehicles parked in the monitored parking lot, the vehicles to be transferred in the monitored parking lot are determined and a transfer reminder message is sent to the corresponding vehicle owners; When the flood risk index of the monitored parking lot is greater than a value in the second value interval, a vehicle transfer prompt message is sent to owners of vehicles parked in the monitored parking lot.
6. The method according to claim 5, It is characterized in that Determining the vehicles to be transferred from the monitored parking lot includes: Determine the minimum threshold value of the number of vehicles to be transferred based on the maximum number of available parking spaces and the number of vehicles already parked in the monitored parking lot; The vehicles to be transferred are determined from the parked vehicles in the monitored parking lot according to the minimum threshold of the number of vehicles to be transferred and the entry time, vehicle type and parking position of the parked vehicles in the monitored parking lot.
7. A parking lot flood risk identification device, It is characterized in that include: A determination module, configured to determine, according to a current position of the target vehicle, a parking lot to be selected that is within a first predetermined range of the current position and has available parking spaces; A prediction module is used to use a pre-built and trained flood risk prediction model to predict flood risks for each of the selected parking lots, and obtain a flood risk index corresponding to each of the selected parking lots, wherein the flood risk prediction model is trained based on corresponding historical hydrological data, historical meteorological data, parking lot attribute information, parking lot flood data, and parking lot flood protection information; the flood risk prediction model includes a number of decision trees, and the corresponding flood risk index is generated by integrating the flood risk prediction results of the decision trees; A selection module, configured to determine at least one target recommended parking lot from the parking lots to be selected according to the flood risk index, the number of available parking spaces, and the distance from the current position of the target vehicle corresponding to each of the parking lots to be selected; The processing module is used to recommend a parking lot according to the at least one target, and generate and push corresponding recommendation information.
8. A computer readable medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for identifying flood risks in a parking lot according to any one of claims 1 to 6 is implemented.
9. An electronic device, It is characterized in that include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the flood risk identification method for a parking lot as described in any one of claims 1 to 6.
Citation Information
Patent Citations
Method and system for preventing vehicle from being flooded based on internet of things big data technology
CN106920416A
Smart city waterlogging information pushing method and device, electronic equipment and storage medium
CN115150463A
Smart sponge system based on coupling numerical simulation and gradient boosting decision tree
CN115456844A
Roof water storage and drainage control method for urban waterlogging prevention
CN117150600A
Electro-absorption modulated lasers with identical-active layer
KR1020240131706A
